相关论文: RTRA: Rapid Training of Regularization-based Appro…

To adapt to real-world data streams, continual learning (CL) systems must rapidly learn new concepts while preserving and utilizing prior knowledge. When it comes to adding new information to continually-trained deep neural networks (DNNs),…

A growing number of state-of-the-art transfer learning methods employ language models pretrained on large generic corpora. In this paper we present a conceptually simple and effective transfer learning approach that addresses the problem of…

Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a…

In recent years, data-driven reinforcement learning (RL), also known as offline RL, have gained significant attention. However, the role of data sampling techniques in offline RL has been overlooked despite its potential to enhance online…

Continual learning (CL) poses the important challenge of adapting to evolving data distributions without forgetting previously acquired knowledge while consolidating new knowledge. In this paper, we introduce a new methodology, coined as…

Continuous-time reinforcement learning (CTRL) provides a natural framework for sequential decision-making in dynamic environments where interactions evolve continuously over time. While CTRL has shown growing empirical success, its ability…

Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same time, SFT may harm the fundamental capabilities of an LLM,…

Over the last years, Deep Learning has been successfully applied to a broad range of medical applications. Especially in the context of chest X-ray classification, results have been reported which are on par, or even superior to experienced…

Large Language Models (LLMs) are emerging as versatile foundation models for computational chemistry, handling bidirectional tasks like reaction prediction and retrosynthesis. However, these models often lack round-trip consistency. For…

Although existing Quantization-Aware Training (QAT) methods intensively depend on knowledge distillation to guarantee performance, QAT still suffers from severe performance drop. The experiments have shown that vanilla quantization is…

Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be shaped not only by…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure the robustness of the reasoning process itself. We adopt a…

Continual Test-Time Adaptation (CTTA) aims to adapt a source pre-trained model to continually changing target domains during inference. As a fundamental principle, an ideal CTTA method should rapidly adapt to new domains (exploration) while…

Large language models (LLMs) exhibit remarkable capabilities in natural language processing but face catastrophic forgetting when learning new tasks, where adaptation to a new domain leads to a substantial decline in performance on previous…

Continual learning (CL) is crucial for evaluating adaptability in learning solutions to retain knowledge. Our research addresses the challenge of catastrophic forgetting, where models lose proficiency in previously learned tasks as they…

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

The main purpose of incremental learning is to learn new knowledge while not forgetting the knowledge which have been learned before. At present, the main challenge in this area is the catastrophe forgetting, namely the network will lose…

Fine-tuning an Automatic Speech Recognition (ASR) model to new domains results in degradation on original domains, referred to as Catastrophic Forgetting (CF). Continual Learning (CL) attempts to train ASR models without suffering from CF.…

World models have recently emerged as a promising approach to reinforcement learning (RL), achieving state-of-the-art performance across a wide range of visual control tasks. This work aims to obtain a deep understanding of the robustness…

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In…